Apparatus and methods for programming and training of robotic household appliances

Patent metadata

Field	Value
Publication number	US-10376117-B2
Application number	US-201715665146-A
Country	US
Kind code	B2
Filing date	Jul 31, 2017
Priority date	Feb 26, 2015
Publication date	Aug 13, 2019
Grant date	Aug 13, 2019

Abstract

Apparatus and methods for training and operating of robotic appliances. Robotic appliance may be operable to clean user premises. The user may train the appliance to perform cleaning operations in constrained areas. The appliance may be configured to clean other area of the premises automatically. The appliance may perform premises exploration and/or determine map of the premises. The appliance may be provided priority information associated with areas of the premises. The appliance may perform cleaning operations in order of the priority. Robotic vacuum cleaner appliance may be configured for safe cable operation wherein the controller may determine one or more potential obstructions (e.g., a cable) along operating trajectory. Upon approaching the cable, the controller may temporarily disable brushing mechanism in order to prevent cable damage.

First claim

What is claimed is:

1. A system for directing a robotic device along a path, comprising:
a memory having computer readable instructions stored thereon; and
a first processor of one or more processors configured to execute the computer readable instructions to:
receive a first input and a second input, the first input corresponding to first information generated by one or more sensors, and the second input corresponding to second information generated by a second processor of the one or more processors;
measure performance of the robotic device continuously in real time by comparing an actual trajectory of the robotic device with a target trajectory of the robotic device, the actual trajectory being determined based on the first information received from the first input, and the target trajectory being determined based on the second information received from the second input;
determine a correction output for the robotic device continuously in real time when the actual trajectory does not match the target trajectory, the correction output based on the first input and the second input; and
output the correction output to the one or more sensors such that the actual trajectory of the robotic device matches the target trajectory of the robotic device.

2. The system of claim 1 , wherein the second information includes the first input and a confidence output, the confidence output includes a confidence information and a motor control information of the robotic device, the confidence information and the motor control information correspond to the actual trajectory of the robotic device, the confidence information includes a measure corresponding to the measure of performance, and the motor control information corresponds to the first information generated by the one or more sensors.

3. The system of claim 1 , wherein the second information is generated when a training input is received, and the training input corresponds to a user input.

4. The system claim 1 , wherein the second information includes a discrepancy output, the discrepancy output is based on comparing a training input with a predetermined output, the training input corresponds to a user input, and the predetermined output is generated by a third processor of the one or more processors.

5. The system of claim 4 , wherein the first processor of the one or more processors is further configured to adjust the output of the correction output such that the first input matches the discrepancy output.

6. The system of claim 1 , wherein:
the second information includes the first input, a confidence output and a discrepancy output;
the confidence output includes a confidence information; and
the confidence information includes a measure corresponding to the measure of performance.

7. The system of claim 1 , wherein the first information generated by the one or more sensors includes at least one or more of audio data, video data, motor torque data, or battery voltage data.

8. A non-transitory computer readable medium having computer readable instructions stored thereon, that when executed by a first processor of one or more processors, cause the first processor of the one or more processors to:
receive a first input and a second input, the first input corresponding to first information generated by one or more sensors, and the second input corresponding to second information generated by a second processor of the one or more processors;
measure a performance of a robotic device continuously in real time by comparing an actual trajectory of the robotic device with a target trajectory of the robotic device, the actual trajectory being determined based on the first information received from the first input, and the target trajectory being determined based on the second information received from the second input;
determine a correction output for the robotic device continuously in real time when the actual trajectory does not match the target trajectory, the correction output based on the first input and the second input; and
output the correction output to the one or more sensors such that the actual trajectory of the robotic device matches the target trajectory of the robotic device.

9. The non-transitory computer readable medium of claim 8 , wherein the second information includes the first input and a confidence output, the confidence output includes a confidence information and a motor control information of the robotic device, the confidence information and the motor control information correspond to the actual trajectory of the robotic device, the confidence information includes a measure corresponding to the measure of performance, and the motor control information corresponds to the first information generated by the one or more sensors.

10. The non-transitory computer readable medium of claim 8 , wherein the second information is generated when a training input is received, and the training input corresponds to a user input.

11. The non-transitory computer readable medium of claim 8 , wherein the second information includes a discrepancy output, the discrepancy output is based on comparing a training input with a predetermined output, the training input corresponds to a user input, and the predetermined output is generated by a third processor of the one or more processors.

12. The non-transitory computer readable medium of claim 11 , wherein the first processor of the one or more processors is further configured to adjust the output of the correction output such that the first input matches the discrepancy output.

13. The non-transitory computer readable medium of claim 8 , wherein: the second information includes the first input, a confidence output and a discrepancy output; the confidence output includes a confidence information; and the confidence information includes a measure corresponding to the measure of performance.

14. The non-transitory computer readable medium of claim 8 , wherein the first information generated by the one or more sensors includes at least one or more of audio data, video data, motor torque data, or battery voltage data.

15. A method for directing a robotic device along a path, comprising:
receiving a first input and a second input, the first input corresponding to first information generated by one or more sensors, and the second input corresponding to second information generated by a first processor of one or more processors;
measuring a performance of the robotic device continuously in real time by comparing an actual trajectory of the robotic device with a target trajectory of the robotic device, the actual trajectory being determined based on the first information received from the first input, and the target trajectory being determined based on the second information received from the second input,
determining a correction output for the robotic device continuously in real time when the actual trajectory does not match the target trajectory, the determining of the correction output comprising determining the correction output based on the first input and the second input, and
transmitting the correction output to the one or more sensors such that the actual trajectory of the robotic device matches the target trajectory of the robotic device.

16. The method of claim 15 , wherein the receiving of the second input corresponds to the second information, the second information includes the first input and a confidence output, the confidence output includes a confidence information and a motor control information of the robotic device, the confidence information and the motor control information correspond

Assignees

• Brain Corp

Inventors

• Szatmary Botond
• Polonichko Vadim

Classifications

• G06N3/049

  Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs · CPC title

• A47L9/2852

  Elements for displacement of the vacuum cleaner or the accessories therefor, e.g. wheels, casters or nozzles · CPC title

• A47L9/2847 Primary

  Surface treating elements · CPC title

• A47L9/2805

  Parameters or conditions being sensed · CPC title

• G06N3/008

  based on physical entities controlled by simulated intelligence so as to replicate intelligent life forms, e.g. based on robots replicating pets or humans in their appearance or behaviour · CPC title